humane-proxy

About humane-proxy

Use humane-proxy with your agent

claude mcp add humane-proxy -- uvx humane-proxy

{
  "mcpServers": {
    "humane-proxy": {
      "command": "uvx",
      "args": [
        "humane-proxy"
      ]
    }
  }
}

Frequently asked questions

What is humane-proxy?

humane-proxy is an MCP (Model Context Protocol) server by vishisht16 in the AI & ML category. AI safety middleware — detects self-harm and criminal intent in LLM prompts.

How do I connect humane-proxy to Claude, Cursor, or another MCP client?

Install humane-proxy from its pypi package (humane-proxy) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.

Is humane-proxy open source?

Yes — the source code is public at github.com/vishisht16/humane-proxy, with 29 GitHub stars.

Can AI agents pay to use humane-proxy?

Not yet through Loomal — humane-proxy is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.